© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63041
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Direction
    -0.47
     positive
    -0.44
    direction
    -0.44
     negative
    -0.43
    negative
    -0.41
    -direction
    -0.41
    Positive
    -0.41
     direction
    -0.41
    positive
    -0.41
    æĸ¹åIJij
    -0.40
    POSITIVE LOGITS
    omat
    0.27
    ledo
    0.27
     chalk
    0.26
    ystone
    0.26
    .API
    0.25
    è¾ĩ
    0.25
    itional
    0.25
    resses
    0.24
    itur
    0.24
    æļĤ
    0.24
    Activations Density 28.846%

    No Known Activations